You can deploy this model and start earning money today!

arelath/
Meta-Llama-3-8B-Instruct-nanoquant-GGUF

Name: Meta-Llama-3-8B-Instruct-nanoquant-GGUF
Availability: InStock

Views

No views yet

Experiment 27: meta-llama/Meta-Llama-3-8B-Instruct quality benchmark

Status: completed
Model: meta-llama/Meta-Llama-3-8B-Instruct
Revision: 8afb486c1db24fe5011ec46dfbe5b5dccdb575c2
Candidate run: /workspace/NanoQuant/evidence/027/027-compress-and-benchmark-meta-llama-3-8b-instruct
Backend: dense
Wall time: 141.53 seconds

completed means all evaluators returned finite metrics; it is not a BF16-quality acceptance gate.

WikiText-2: 64 samples × 128 tokens, batch 8
WikiText token hash: sha256:c7dc8810186996593a9a8a419db6bcae8e67e520c2412722425817fc5862a77d
Tasks: piqa, arc_easy, arc_challenge, hellaswag, winogrande, boolq; first 200 rows, batch 4
Tokenizer hash: sha256:8aa3159f5493d3660d5f6898b3b1a88d5b1626e4ac1f7dd5b60fed8f916080df

Benchmark	Metric	BF16	NanoQuant	Delta	Ratio
WikiText-2	perplexity ↓	24.956664	55.331093	+30.374429 (+121.71%)	2.2171x
piqa	acc_norm ↑	0.7700	0.6800	-0.0900	0.8831x
arc_easy	acc_norm ↑	0.7550	0.4850	-0.2700	0.6424x
arc_challenge	acc_norm ↑	0.5150	0.2900	-0.2250	0.5631x
hellaswag	acc_norm ↑	0.6550	0.5500	-0.1050	0.8397x
winogrande	acc ↑	0.7150	0.6350	-0.0800	0.8881x
boolq	acc ↑	0.8300	0.7400	-0.0900	0.8916x

Model	Elapsed seconds	Peak CUDA bytes	Peak host bytes
BF16	29.73	18,194,890,752	33,399,840,768
NanoQuant	35.35	18,803,064,832	33,399,840,768

Experiment config hash: sha256:801c828f06b50662d77573ed177f639142880d06b9d4f440261babe50ab94b96
Launcher: experiments/027-compress-and-benchmark-meta-llama-3-8b-instruct.py
Candidate identity: {"config_hash":"sha256:044785fa22c02ddeb31c43cffde7172becdc19475a8e342b0a8344613a6ef2fb","model_hash":"sha256:d590dbc8c4a1851df6feb003b377003e7e4ededacc99ed35abb96844d236322d","plan_hash":"sha256-57b3f751fb9b821e18abad776ffc22f4f90d5b6d73378e90037728ca2b1cdcbb"}
Global tuning: {"artifact_id":"sha256-68defbc90a8e75e2a59b51d40c054cff9bc393012039641fa3365b32787509e7","artifact_type":"global-tuning-result","schema_version":1}